CN109591794B - Intelligent start-stop method and system - Google Patents
Intelligent start-stop method and system Download PDFInfo
- Publication number
- CN109591794B CN109591794B CN201710917530.6A CN201710917530A CN109591794B CN 109591794 B CN109591794 B CN 109591794B CN 201710917530 A CN201710917530 A CN 201710917530A CN 109591794 B CN109591794 B CN 109591794B
- Authority
- CN
- China
- Prior art keywords
- state
- vehicle
- traffic
- speed
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000002401 inhibitory effect Effects 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000003139 buffering effect Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W10/00—Conjoint control of vehicle sub-units of different type or different function
- B60W10/04—Conjoint control of vehicle sub-units of different type or different function including control of propulsion units
- B60W10/06—Conjoint control of vehicle sub-units of different type or different function including control of propulsion units including control of combustion engines
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18018—Start-stop drive, e.g. in a traffic jam
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18154—Approaching an intersection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D17/00—Controlling engines by cutting out individual cylinders; Rendering engines inoperative or idling
- F02D17/04—Controlling engines by cutting out individual cylinders; Rendering engines inoperative or idling rendering engines inoperative or idling, e.g. caused by abnormal conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo or light sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/60—Traffic rules, e.g. speed limits or right of way
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2710/00—Output or target parameters relating to a particular sub-units
- B60W2710/06—Combustion engines, Gas turbines
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an intelligent start-stop method and system, wherein the system comprises a camera and a processor for collecting and analyzing images acquired by the camera, and the specific method comprises the following steps: s1, identifying whether a traffic light exists in front of the vehicle or not and the state of the traffic light in an image identification mode; obtaining the speed of the vehicle within the image recognition range through an image recognition mode, and meanwhile, determining the road congestion state by combining the speed of the vehicle and the traffic light state; s2, when the current road congestion state is judged to be traffic congestion, inhibiting the intervention of a start-stop system; otherwise, judging that the current road congestion state is good, and allowing the start-stop system to intervene. The invention has the following beneficial effects: 1. the states of the front vehicle target and the traffic light are obtained by combining the visual processing of the camera on the front, so that the current traffic environment is judged, and most importantly, whether the current traffic environment is in a traffic jam state or not is obtained, so that the problem that the start and stop system frequently starts and stops when the traffic jam occurs, which is widely complained by the start and stop system, is solved.
Description
Technical Field
The invention relates to the field of automobile energy-saving systems, in particular to an intelligent starting and stopping method and system.
Background
The start-stop system aims at shutting down the engine when the engine is idling. When the engine stops running, the start-stop system controls the automobile not to consume fuel and generate emission, the conventional start-stop system is a set of system for controlling the vehicle power assembly to start and stop, the state of the vehicle is judged through the control unit, for example, the vehicle is in a stop state such as a red light, a blockage and the like, the system controls the engine to automatically stop running, the transmission case cuts off power transmission, when a driver has a starting requirement, for example, when a brake pedal is released or an accelerator pedal is stepped on, the engine is restarted immediately, the transmission case simultaneously responds to the starting requirement of the engine, the clutch is rapidly engaged, and comfortable starting is ensured. The start-stop system closes the engine when the vehicle idles, reduces fuel consumption and carbon dioxide emission when the engine idles, reduces vehicle noise, and relevant experiments prove that the start-stop system can reduce about 8% of energy consumption and emission under comprehensive working conditions, the energy-saving effect in congested urban areas can reach 10% -15%, the incremental cost of installing the start-stop system is not large, the change to the existing power transmission system is small, but the start-stop system is very suitable for running under urban road conditions, and has very strong practical value, and except the advantage of saving oil, the start-stop system more conforms to the construction of a low-carbon society advocated at present.
However, most of the current engine start-stop technologies are from abroad, have better performance under good road conditions in europe or america and the like, but under more complicated road conditions in china, especially under particularly congested road conditions, the start-stop technologies cannot play the original role of energy saving, and because the start-stop technologies are frequently started and stopped during congestion, the driving comfort of users is greatly reduced.
In the prior art, in order to improve the practicability, a mode of combining with a vehicle network is adopted in part of solutions, and the road congestion condition of the current position of a vehicle is acquired through the network to control the start or stop of a system. However, this method requires the addition of a telecommunication system and has high requirements for the network, and the practical application is not very significant.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent starting and stopping method and system.
An intelligent start-stop method is characterized in that a road congestion state and a traffic light identification state are acquired through image data in front of a vehicle, so that intervention of a start-stop system is allowed or inhibited; the method for acquiring the road congestion state and the traffic light identification state comprises the following steps:
s1, identifying whether a traffic light exists in front of the vehicle or not and the state of the traffic light in an image identification mode; obtaining the speed of the vehicle within the image recognition range through an image recognition mode, and meanwhile, determining the road congestion state by combining the speed of the vehicle and the traffic light state;
s2, when the current road congestion state is judged to be traffic congestion, inhibiting the intervention of a start-stop system; otherwise, judging that the current road congestion state is good, and allowing the start-stop system to intervene.
Further, the determination of the congestion status of the single link in step S1 includes at least one of the following determination conditions:
when the speed of the self automobile and the speed of the automobile in the image recognition range are less than a low speed threshold value and are in a non-red light state, judging that the automobile is in a traffic jam state;
and when the current speed of the self automobile or the automobile speed in the image recognition range is larger than the high-speed threshold value or the current red light state, judging that the road condition is in a good state.
As a further optimization of the above method, the road congestion state further comprises a temporary congestion state, and when in the temporary congestion state, the start-stop system intervention is allowed.
Further, the determination of the congestion status of the single link in step S1 includes at least one of the following determination conditions:
when the speed of the self automobile and the speed of the automobile in the image recognition range are less than a low speed threshold value and are in a non-red light state, judging that the automobile is in a traffic jam state;
when the current speed of the self automobile or the speed of the automobile in the image recognition range is larger than a high-speed threshold value, judging that the road condition is in a good state;
when the road congestion state is in a good road condition and meets the traffic congestion state, the temporary congestion state needs to be entered first, and when the time length in the temporary congestion state exceeds a first buffering threshold value, the traffic congestion state is judged;
and when the road congestion state is in traffic congestion, the time when the speed of the road is zero exceeds a second buffer threshold value, or the road congestion state is in a red light state currently, the temporary congestion state is determined.
As a further refinement of the above method, the method for recognizing the traffic light state within the image recognition range in step S1 includes the following steps:
s111, acquiring image information in front of the vehicle at the current moment, and preprocessing the image information;
s112, detecting the traffic lights through an HOG characteristic detection method, and marking the detected traffic lights and segmenting an identification area image if the traffic lights exist in the current image information;
and S113, analyzing and identifying the signal type of the traffic light in the area image through a convolutional neural network, and outputting.
As a further refinement of the above method, the method for recognizing the vehicle within the image recognition range in step S1 includes the steps of:
s121, acquiring image information in front of the vehicle at the current moment, and preprocessing the image information;
s122, detecting the vehicles in the image by using an HOG feature detection method, and marking the detected vehicles if the vehicles exist in the current image information;
and S123, acquiring the actual relative position and distance between the front vehicle and the vehicle according to the direction and the area of the vehicle in the image.
Wherein the step S122 includes the following substeps:
s1221, carrying out standardization processing on the GAMMA space and the color space of the image;
s1222, calculating image gradients, and constructing a gradient direction histogram for each cell unit;
s1223, combining the cell units into a large block, and normalizing the gradient histogram in the block;
s1224, statistics and analysis of HOG characteristics, and accordingly vehicle detection is achieved.
Further, the vehicles in the image recognition range comprise vehicles right in front of the automobile and/or vehicles in front of adjacent lanes.
Preferably, the low-speed threshold value is any value between 10km/h and 20 km/h; the high-speed threshold value is any value between 28km/h and 32 km/h; the first buffering threshold value is 1 min; the second buffering threshold is 1 min.
In addition, the invention also provides an intelligent start-stop system, which comprises a camera and a processor for acquiring and analyzing the images acquired by the camera; the working method of the processor adopts the intelligent start-stop method.
The intelligent starting and stopping method and system have the beneficial effects that:
1. according to the invention, the states of the front vehicle target and the traffic light are obtained by combining the visual processing of the camera on the front, so that the current traffic environment is judged, and most importantly, whether the current traffic environment is in a traffic jam state or not is obtained, so that the problem that the start and stop system is frequently started and stopped when the traffic jam occurs, which is widely complained by the start and stop system, is solved.
2. By applying the method, 90% of start-stop actions during congestion can be avoided, and the service lives of an engine, a start-stop system and an animal battery are prolonged.
Drawings
Fig. 1 is a schematic diagram of an intelligent start-stop system architecture in embodiment 1 of the present invention.
Fig. 2 is a schematic diagram of a method in embodiment 2 of the present invention.
Fig. 3 is a schematic diagram of vehicle detection in embodiment 2 of the present invention.
Fig. 4 is a schematic diagram illustrating a road congestion state transition in embodiment 3 of the present invention.
Fig. 5 is a flowchart of a traffic light status identification method in embodiment 4 of the present invention.
Fig. 6 is a diagram of the convolutional neural network analysis architecture in embodiment 4 of the present invention.
Fig. 7 is a flowchart of a method for identifying a relative position of a vehicle and a vehicle speed in embodiment 5 of the present invention.
Fig. 8 is a flowchart of an HOG vehicle detection method according to embodiment 5 of the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand for those skilled in the art and will therefore make the scope of the invention more clearly defined.
Example 1:
this implementation provides an intelligence opens and stops system, and this intelligence opens and stops system as shown in fig. 1, and it includes camera, treater and start control ware.
Wherein, the starting control is used for controlling ignition and flameout of the engine according to instructions of the processor, and the camera is arranged at the position right in front of the automobile or the front windshield. The camera adopted by the embodiment is a monocular camera, and can realize the image acquisition of the distance of 160 meters ahead and the coverage angle of 50 degrees. Therefore, the method is applied to visual detection such as lane detection, front vehicle detection, traffic sign identification and the like.
The processor judges the congestion state of the current road and the traffic light state in the front after acquiring the image acquired by the camera, so that whether the start-stop system is allowed to be accessed to the driving process or not is controlled by combining the traffic light state and the congestion state, the intelligent degree and the practical degree of the start-stop system are greatly improved, the advantage of the start-stop system is brought to play when the traffic light is normally waited for, and the trouble brought to a user by frequent start and stop when the traffic light is congested is reduced.
Example 2:
on the basis of embodiment 1, the embodiment provides an intelligent start-stop method, which obtains a road congestion state of a current position type road section of an automobile by analyzing image data of the front of the automobile, identifies the state of a traffic light if the road section has the traffic light, and then allows or inhibits intervention of a start-stop system according to an identification result. Specifically, as shown in fig. 2, the acquiring the road congestion state and the traffic light identification state includes the following steps:
and S1, on one hand, judging whether a traffic light exists in front of the vehicle in an image recognition mode, and if so, recognizing the state of the traffic light. On the other hand, the vehicle speed of the vehicle within the image recognition range is obtained by the image recognition method. Meanwhile, the road congestion state is judged by combining the speed of the vehicle and the state of the traffic light.
In the embodiment, the vehicles in the image recognition range include vehicles in front of the automobile and/or vehicles in front of adjacent lanes, as shown in fig. 3.
The road congestion state includes a state of good road condition and a state of traffic congestion.
S2, after the identification of the current road congestion state is completed, when the current road congestion state is judged to be traffic congestion, the intervention of a start-stop system is inhibited; otherwise, judging that the current road congestion state is good, and allowing the start-stop system to intervene.
The present embodiment determines the road congestion state as follows:
firstly, judging the traffic jam state: when the speed of the self automobile and the speed of the automobile in the image recognition range are less than a low speed threshold value and are in a non-red light state, judging that the automobile is in a traffic jam state;
and the judgment of the good road condition is as follows: and when the current speed of the self automobile or the automobile speed in the image recognition range is larger than the high-speed threshold value or the current red light state, judging that the road condition is in a good state.
Preferably, the low-speed threshold value in the embodiment is an arbitrary value between 10km/h and 20 km/h; further preferably 15 km/h. The high speed threshold is an arbitrary value between 28km/h and 32 km/h, and more preferably 30 km/h.
Example 3:
as an optimization of embodiment 2, the present embodiment is different from embodiment 1 in that: as shown in fig. 4, the road congestion status is defined and divided into three states of good road condition, temporary congestion and traffic congestion. The temporary congestion state is added to provide a buffer state between the good road condition and the traffic congestion state, so that the start-stop system is more stable and reliable, and the congestion increase condition is avoided.
When the road condition is good and the traffic jam is temporary, the system still allows the intervention of the start-stop system, namely when the intervention requirement of the start-stop system is met, the automobile still stops and stops. When the automobile is in a traffic jam state, the automobile can not stop and flameout by inhibiting the intervention of the start-stop system, namely, the intervention requirement of the start-stop system is met in time.
Specifically, referring to fig. 4, the transition conditions between the above three states are as follows:
condition 1: the speed of the vehicle is less than the low-speed threshold, the speed of the vehicle right in front of the vehicle is less than the low-speed threshold, the number of the vehicles on the left and the right is more than or equal to 2, the speed of the vehicles on the left and the right is less than the low-speed threshold, and the current state of the red lights is unequal.
Condition 2: the speed of the motor vehicle is greater than or equal to a high-speed threshold value, or the speed of the vehicle right in front of the motor vehicle is a high-speed threshold value, or the number of left and right vehicles is less than 2, or the speed of the left and right vehicles is a high-speed threshold value, or the motor vehicle is in a red light waiting state at present.
Condition 3: the system is in the temporary congestion state for a time greater than or equal to a first buffer time.
Condition 4: the time of the self-speed is 0km/h continuously exceeds the second buffer time, or the front is in a red light waiting state.
Condition 5: the speed of the vehicle is greater than or equal to a high speed threshold value, or the speed of the vehicle in front of the vehicle is greater than or equal to the high speed threshold value, or the number of left and right vehicles is less than 2, or the speed of the left and right vehicles is greater than or equal to the high speed threshold value.
In this embodiment, the first buffer time is 1 minute, and the second buffer time is 1 minute.
Example 4:
in addition to embodiments 2 and 3, the present embodiment differs from embodiment 2 or 3 in that: the present embodiment provides the method for recognizing the traffic light state within the image recognition range in step S1, including the following steps, as shown in fig. 5 and 6:
and S111, activating the camera, acquiring image information in front of the vehicle at the current moment, and preprocessing the image information.
And S112, detecting the traffic lights through a HOG (Histogram of Oriented Gradient) feature detection method, and marking the detected traffic lights and segmenting an identification area image if the traffic lights exist in the current image information.
And S113, analyzing and identifying the signal type of the traffic light in the area image through a convolutional neural network, wherein the convolutional neural network analysis is as shown in FIG. 6, and after the segmented identification area image is analyzed through a down-sampling layer, the segmented identification area image finally returns to one of three traffic light signals to be output.
Example 5:
in addition to embodiments 2 and 3, the present embodiment differs from embodiment 2 or 3 in that: in step S1, the method for recognizing a vehicle in the image recognition range by using an HOG + SVM (Support Vector Machine) method to detect an object of the vehicle ahead, as shown in fig. 7, and the step of giving the vehicle position includes the following steps:
s121, acquiring image information in front of the vehicle at the current moment, and preprocessing the image information;
s122, detecting the vehicles in the image by using an HOG feature detection method, and marking the detected vehicles if the vehicles exist in the current image information;
and S123, acquiring the actual relative position and distance between the front vehicle and the host vehicle according to the direction and area of the vehicle in the image, and analyzing the position of the front vehicle in the image to acquire the actual relative distance between the front vehicle and the host vehicle in a pre-vertex mode in the aspect of relative position analysis. After the relative position of the vehicle is determined, contact capture and tracking of the vehicle in front is achieved by acquiring and analyzing a plurality of images in continuous time. And recording the change of the relative distance between the front vehicle and the vehicle in a preset time period. Therefore, the speed of the front vehicle is judged by combining the real-time speed of the vehicle.
With reference to fig. 8, in the step of detecting HOG features, S122 specifically includes the following sub-steps:
s1221, carrying out standardization processing on the GAMMA space and the color space of the image;
s1222, calculating image gradients, and constructing a gradient direction histogram for each cell unit;
s1223, combining the cell units into a large block, and normalizing the gradient histogram in the block;
s1224, statistics and analysis of HOG characteristics, and accordingly vehicle detection is achieved.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. An intelligent start-stop method is characterized in that a road congestion state and a traffic light identification state are acquired through image data in front of a vehicle, so that intervention of a start-stop system is allowed or inhibited; the method is characterized in that: the method for acquiring the road congestion state and the traffic light identification state comprises the following steps:
s1, identifying whether a traffic light exists in front of the vehicle or not and the state of the traffic light in an image identification mode; obtaining the speed of the vehicle within the image recognition range through an image recognition mode, and meanwhile, determining the road congestion state by combining the speed of the vehicle and the traffic light state;
s2, when the current road congestion state is judged to be traffic congestion, inhibiting the intervention of a start-stop system; otherwise, when the current road congestion state is judged to be a good road condition or a temporary congestion state, the intervention of the start-stop system is allowed; the temporary congestion state is a buffer state between a good road condition state and a traffic congestion state;
when the road congestion state is in a good road condition and meets the traffic congestion state, the temporary congestion state needs to be entered first, and when the time length in the temporary congestion state exceeds a first buffer threshold value, the traffic congestion state is judged;
and when the road congestion state is in traffic congestion, and the time when the speed of the road is zero exceeds a second buffer threshold value, or the road congestion state is currently in a red light state, determining the road congestion state as a temporary congestion state.
2. The intelligent start-stop method according to claim 1, wherein the determination of the road congestion state in step S1 includes at least one of the following determination conditions:
when the speed of the self automobile and the speed of the automobile in the image recognition range are less than a low speed threshold value and are in a non-red light state, judging that the automobile is in a traffic jam state;
and when the current speed of the self automobile or the automobile speed in the image recognition range is larger than the high-speed threshold value or the current red light state, judging that the road condition is in a good state.
3. The intelligent start-stop method according to claim 1, wherein the determination of the road congestion state in step S1 includes at least one of the following determination conditions:
when the speed of the self automobile and the speed of the automobile in the image recognition range are less than a low speed threshold value and are in a non-red light state, judging that the automobile is in a traffic jam state;
and when the current speed of the self automobile or the speed of the automobile in the image recognition range is larger than the high-speed threshold value, judging that the road condition is in a good state.
4. The intelligent start-stop method according to any one of claims 1-3, wherein the method for identifying the traffic light state in the image identification range in the step S1 comprises the following steps:
s111, acquiring image information in front of the vehicle at the current moment, and preprocessing the image information;
s112, detecting the traffic lights through an HOG characteristic detection method, and marking the detected traffic lights and segmenting an identification area image if the traffic lights exist in the current image information;
and S113, analyzing and identifying the signal type of the traffic light in the area image through a convolutional neural network, and outputting.
5. The intelligent start-stop method according to any one of claims 1-3, characterized in that the method for identifying the vehicles within the image identification range in the step S1 comprises the following steps:
s121, acquiring image information in front of the vehicle at the current moment, and preprocessing the image information;
s122, detecting the vehicles in the image by using an HOG feature detection method, and marking the detected vehicles if the vehicles exist in the current image information;
and S123, acquiring the actual relative position and distance between the front vehicle and the vehicle according to the direction and the area of the vehicle in the image.
6. The intelligent start-stop method according to claim 5, wherein the step S122 comprises the following sub-steps:
s1221, carrying out standardization processing on the GAMMA space and the color space of the image;
s1222, calculating image gradients, and constructing a gradient direction histogram for each cell unit;
s1223, combining the cell units into a large block, and normalizing the gradient histogram in the block;
s1224, statistics and analysis of HOG characteristics, and accordingly vehicle detection is achieved.
7. The intelligent start-stop method according to claim 1, characterized in that the vehicles in the image recognition range comprise vehicles in front of the automobile and/or vehicles in front of adjacent lanes.
8. The intelligent start-stop method according to claim 1, characterized in that the first buffer threshold is 1 min; the second buffering threshold is 1 min.
9. The intelligent start-stop method according to claim 2, wherein the low speed threshold is any value between 10km/h and 20 km/h; the high-speed threshold value is any value between 28km/h and 32 km/h.
10. An intelligent start-stop system comprises a camera and a processor for acquiring and analyzing images acquired by the camera; characterized in that an intelligent start-stop method according to claim 1 is used.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710917530.6A CN109591794B (en) | 2017-09-30 | 2017-09-30 | Intelligent start-stop method and system |
| PCT/CN2017/108074 WO2019061631A1 (en) | 2017-09-30 | 2017-10-27 | Smart start-stop method and system |
| US16/614,372 US20200079374A1 (en) | 2017-09-30 | 2017-10-27 | Intelligent stop and start (stt) system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710917530.6A CN109591794B (en) | 2017-09-30 | 2017-09-30 | Intelligent start-stop method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109591794A CN109591794A (en) | 2019-04-09 |
| CN109591794B true CN109591794B (en) | 2021-03-02 |
Family
ID=65900423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710917530.6A Active CN109591794B (en) | 2017-09-30 | 2017-09-30 | Intelligent start-stop method and system |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20200079374A1 (en) |
| CN (1) | CN109591794B (en) |
| WO (1) | WO2019061631A1 (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019073583A1 (en) | 2017-10-12 | 2019-04-18 | 日産自動車株式会社 | Method and apparatus for controlling automated vehicle |
| CN111148675B (en) * | 2017-10-26 | 2023-07-25 | 日产自动车株式会社 | Control method and control device for automatic driving vehicle |
| US11195030B2 (en) | 2018-09-14 | 2021-12-07 | Honda Motor Co., Ltd. | Scene classification |
| US11034357B2 (en) * | 2018-09-14 | 2021-06-15 | Honda Motor Co., Ltd. | Scene classification prediction |
| CN111845742B (en) * | 2019-04-22 | 2021-11-23 | 上海汽车集团股份有限公司 | Car following control system and method for intelligent driving car |
| CN110395252B (en) * | 2019-08-06 | 2021-02-19 | 华北理工大学 | Automatic vehicle passing control system and method for traffic light intersection |
| CN113936451A (en) * | 2020-06-29 | 2022-01-14 | 南宁富桂精密工业有限公司 | Traffic detection system and traffic detection method |
| CN112622847B (en) * | 2020-12-28 | 2022-01-28 | 重庆工商大学 | Automatic parking control method, device and equipment and readable storage medium |
| CN112829749A (en) * | 2021-01-25 | 2021-05-25 | 北京汽车研究总院有限公司 | Vehicle, automatic start-stop control method and system of engine of vehicle and storage medium |
| CN115075960A (en) * | 2021-03-15 | 2022-09-20 | 智博汽车科技(上海)有限公司 | Engine start-stop control method and device and vehicle |
| CN114165343A (en) * | 2021-11-05 | 2022-03-11 | 一汽奔腾轿车有限公司 | Method for adjusting and controlling vehicle idle speed start-stop system |
| CN114291089A (en) * | 2021-12-15 | 2022-04-08 | 清华大学苏州汽车研究院（吴江） | Automatic start-stop method and device integrating image recognition |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3633306B2 (en) * | 1998-09-18 | 2005-03-30 | トヨタ自動車株式会社 | Vehicle engine control device |
| JP2001107769A (en) * | 1999-10-04 | 2001-04-17 | Honda Motor Co Ltd | Engine control device |
| EP1227230B1 (en) * | 2001-01-26 | 2006-07-19 | Denso Corporation | Engine control apparatus |
| DE102008006028A1 (en) * | 2008-01-25 | 2009-07-30 | Robert Bosch Gmbh | Method and device for automatically switching on and off an internal combustion engine |
| DE102008031340A1 (en) * | 2008-07-02 | 2010-01-07 | Bayerische Motoren Werke Aktiengesellschaft | Method for influencing engine stop mechanism of motor vehicle, involves switching off engine automatically, when predetermined operating conditions are achieved for predetermined time |
| CN102582619B (en) * | 2012-02-28 | 2014-11-26 | 浙江吉利汽车研究院有限公司 | Automobile starting/stopping system with traffic light identifying function and control method thereof |
| CN104791113B (en) * | 2015-03-20 | 2017-06-13 | 武汉理工大学 | Engine automatic start-stop Intellective method for triggering and system based on traveling road conditions |
| CN106184213A (en) * | 2016-09-23 | 2016-12-07 | 戴姆勒股份公司 | The control method of start stop system and start stop system |
| CN106335510A (en) * | 2016-09-29 | 2017-01-18 | 北京汽车股份有限公司 | Car and control system and method for automatic starting-stopping function of engine of car |
-
2017
- 2017-09-30 CN CN201710917530.6A patent/CN109591794B/en active Active
- 2017-10-27 WO PCT/CN2017/108074 patent/WO2019061631A1/en active Application Filing
- 2017-10-27 US US16/614,372 patent/US20200079374A1/en not_active Abandoned
Also Published As
| Publication number | Publication date |
|---|---|
| CN109591794A (en) | 2019-04-09 |
| WO2019061631A1 (en) | 2019-04-04 |
| US20200079374A1 (en) | 2020-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109591794B (en) | Intelligent start-stop method and system | |
| US8185296B2 (en) | Driving assisting apparatus and driving assisting method | |
| CN111899530B (en) | Traffic light control method, system, mobile terminal and storage medium | |
| CN110533946B (en) | Single-point intersection vehicle speed optimization method under mixed-traveling environment based on edge calculation | |
| CN103786726B (en) | Intuitive energy-saving driving assisting method and intuitive energy-saving driving assisting system | |
| CN104791113A (en) | Automatic engine start and stop intelligent trigger method and system based on driving road condition | |
| CN111038488B (en) | Energy optimization control method and device for hybrid electric vehicle | |
| CN106837649A (en) | Self study intelligence start stop system based on signal lamp countdown identification | |
| CN106740842A (en) | A kind of petroleum economizer and method for self-adaption cruise system | |
| CN111754790B (en) | Ramp entrance traffic control system and method based on radar | |
| CN110723143B (en) | Economical self-adaptive cruise control system and method suitable for multiple driving conditions | |
| TWI505958B (en) | Intuitive energy - saving driving aids and systems | |
| CN114519936B (en) | Traffic light intersection engine start and stop intelligent control method and system based on V2X | |
| CN109291917B (en) | Intelligent control method for matching operation of automatic driving air throttle with brake | |
| CN114435379B (en) | Economical driving control method and device for vehicle | |
| CN113771854A (en) | Intelligent judgment method and system for automobile start-stop working condition | |
| CN110853372A (en) | Intelligent speed-limiting alarm method and device thereof | |
| CN114435355A (en) | Intelligent driving control method based on headlamp identification and storage medium | |
| CN111027365B (en) | Positioning method based on human face object position analysis | |
| CN110723153A (en) | Individualized driving habit learning system based on environmental information and vehicle motion | |
| CN111785048A (en) | Public transport priority processing system and method based on human-vehicle-road cooperation | |
| CN114017187B (en) | Engine start-stop control method and device and vehicle | |
| CN206231380U (en) | A kind of intelligence may be selected the safe backing device of constant speed | |
| CN114435365A (en) | Engine start-stop control system and method based on driving environment | |
| CN115798205A (en) | Vehicle intelligent start-stop control method, control system and control device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |